Litcius/Paper detail

ST-GPINN: a spatio-temporal graph physics-informed neural network for enhanced water quality prediction in water distribution systems

Tianwei Mu, Feiyu Duan, Baokuan Ning, Bo Zhou, Junyu Liu, Manhong Huang

2025npj Clean Water21 citationsDOIOpen Access PDF

Abstract

Data-driven models often neglect the underlying physical principles, limiting generalization capabilities in water distribution systems (WDSs). This study presents a novel spatio-temporal graph physics-informed neural network (ST-GPINN) for water quality prediction in WDSs, integrating hydraulic simulations, physics-informed neural networks (PINNs), and graph neural networks (GNNs) to capture dynamics and graph-based network connectivity while approximating partial differential equations (PDEs). ST-GPINN discretizes WDSs using virtual nodes to enhance spatial granularity, employs an Encoder-Processor-Decoder architecture for predictions. Validated on Network A (a small-scale network with 9 junctions and 11 pipes) and Network B (a real large-scale WDS with 920 junctions and 1032 pipes), ST-GPINN outperforms others, achieving a MAE of 0.0073 mg/L, RMSE of 0.0121 mg/L, and R2 of 88.91% in Network A, and a MAE of 0.008 mg/L, RMSE of 0.0098 mg/L, and R² of 98.91% in Network B. Its scalability and accuracy highlight ST-GPINN’s potential for water quality predictions.

Topics & Concepts

Water qualityArtificial neural networkGraphDistribution (mathematics)Computer scienceArtificial intelligenceStatistical physicsPhysicsMathematicsTheoretical computer scienceBiologyEcologyMathematical analysisHydrological Forecasting Using AITraffic Prediction and Management TechniquesWater Quality Monitoring Technologies
ST-GPINN: a spatio-temporal graph physics-informed neural network for enhanced water quality prediction in water distribution systems | Litcius